Geekbench ML Score

5482
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 19 2024 12:19 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model Micro-Star International Co., Ltd. MS-7D69
Motherboard Micro-Star International Co., Ltd. MEG X670E ACE (MS-7D69)
Power PlanBalanced
CPU Information
Name AMD Ryzen 9 9950X 16-Core Processor
Topology 1 Processor, 16 Cores, 32 Threads
Identifier AuthenticAMD Family 26 Model 68 Stepping 0
Base Frequency 4.30 GHz
Cluster 116 Cores
L1 Instruction Cache32.0 KB x 16
L1 Data Cache48.0 KB x 16
L2 Cache1.00 MB x 16
L3 Cache32.0 MB x 2
Memory Information
Size 64.00 GB
Inference Information
Framework ONNX
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2186
409.1 IPS
 
Image Classification (F16)
100% 2190
409.7 IPS
 
Image Classification (I8)
99% 5592
1.05 KIPS
 
Image Segmentation (F32)
100% 2330
38.9 IPS
 
Image Segmentation (F16)
100% 2325
38.8 IPS
 
Image Segmentation (I8)
98% 3058
51.1 IPS
 
Pose Estimation (F32)
100% 18510
22.4 IPS
 
Pose Estimation (F16)
100% 18573
22.5 IPS
 
Pose Estimation (I8)
100% 55091
66.7 IPS
 
Object Detection (F32)
100% 2420
180.7 IPS
 
Object Detection (F16)
100% 2396
178.9 IPS
 
Object Detection (I8)
62% 2601
194.1 IPS
 
Face Detection (F32)
100% 4144
49.3 IPS
 
Face Detection (F16)
100% 4150
49.3 IPS
 
Face Detection (I8)
89% 6179
73.5 IPS
 
Depth Estimation (F32)
100% 11067
85.8 IPS
 
Depth Estimation (F16)
100% 10984
85.2 IPS
 
Depth Estimation (I8)
96% 25199
195.4 IPS
 
Style Transfer (F32)
100% 30139
39.6 IPS
 
Style Transfer (F16)
100% 29335
38.6 IPS
 
Style Transfer (I8)
98% 41677
54.8 IPS
 
Image Super-Resolution (F32)
100% 4066
145.2 IPS
 
Image Super-Resolution (F16)
100% 4610
164.7 IPS
 
Image Super-Resolution (I8)
99% 6102
217.9 IPS
 
Text Classification (F32)
100% 1936
2.78 KIPS
 
Text Classification (F16)
100% 1740
2.50 KIPS
 
Text Classification (I8)
98% 497
714.1 IPS
 
Machine Translation (F32)
100% 3443
63.4 IPS
 
Machine Translation (F16)
100% 3498
64.4 IPS
 
Machine Translation (I8)
67% 4208
77.4 IPS
 

Compare

Set Baseline Geekbench 6 now available